Search arXiv⌕ Search

arXiv subjects

Yue Liu

Publications and source records attributed to Yue Liu.

At least 19 recordsLinked to original sources
arXiv2026

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under serious scrutiny: a recent audit found that nearly 60% of unsolved SWE-bench Verified instances contain flawed tests -- either overly narrow tests that reject correct solutions or overly broad tests that check unstated requirements -- and that frontier models can verbatim reproduce gold patches from training data. Code refactoring, which requires coordinated, behavior-preserving changes across many files, offers a substantially harder and more realistic test of agent capability, yet remains underserved by current benchmarks. We introduce SWE-Bench ProMax, an expert-curated, multilingual code refactoring benchmark of 170 instances drawn from real commits across seven programming languages (Python, Java, TypeScript, Go, C, C++, and Rust). Every instance undergoes rigorous, multi-stage curation that directly addresses the quality problems identified in prior benchmarks: issue descriptions are rewritten from scratch to provide precise, unambiguous specifications, and test suites are manually reviewed to remove overly narrow and overly broad tests. Tasks with insufficient complexity or limited cross-file scope are filtered out, yielding a benchmark of challenging, large-scale refactoring tasks that average 11.5 modified files and 261.6 lines of code per instance, substantially exceeding the scale of existing benchmarks. Experiments with frontier models under two agent scaffolds show that the best model achieves only 41.2% resolve rate, confirming that SWE-Bench ProMax presents a meaningful and unsaturated challenge for current AI coding agents. Our benchmark is available at https://huggingface.co/datasets/swe-bench-promax/SWE-Bench-ProMax.

cs.CL↗
arXiv2026

Rethinking Positional Encoding and Interaction Granularity for CTR Prediction

Click-through rate (CTR) prediction relies on historical behaviors and contextual features to estimate clicks on a target item. Existing Transformer-based CTR models often adopt index-based or temporal positional encodings and token-level causal interaction. However, we observe that most existing positional encodings do not outperform NoPE, while relaxing causal constraints within target-relative temporal groups also yields gains. These observations motivate a fundamental question: what positional encoding and interaction granularity does CTR prediction actually require? To address this question, we propose \textbf{TRIP}, which combines target-aware rank--time positional encoding with temporal-group interaction modeling. Specifically, Factorized Rank Encoding represents each behavior's ordinal position within the historical sequence through a low-rank factorization, while Target-Relative Time Encoding characterizes its temporal distance to the target on a coarse-to-fine scale. This joint design grounds each behavior's positional representation in its sequence context and temporal relation to the current target. Furthermore, Temporal Group-Causal Interaction enriches intra-group representations through bidirectional interaction and masked reconstruction while preserving inter-group causal order. Finally, behavior representations are condensed into compact group summaries for efficient group-level modeling in subsequent layers. Experiments on four public benchmarks show that TRIP improves AUC by up to 4.45\% relative to the strongest baseline.

cs.IR↗
arXiv2026

EmbodiedLab: Benchmarking Embodied Agents That Act to Know

Embodied agents are expected to accomplish real-world goals by deciding for themselves how and when to interact with their surroundings. For many such goals, changing the physical state of the world is the means rather than the end: the agent changes the state of a system through interaction, observes the feedback, and explores until it either achieves the goal itself (e.g., discovering physical laws) or learns what the goal requires; it acts to know. Manipulation benchmarks stop at acting to change, with the target state given; scientific discovery benchmarks evaluate knowing but replace physical experimentation with symbolic actions or numerical queries. We introduce EmbodiedLab, a benchmark in which a robot must act to know. Quantitative science experiments make this setting controllable: the parameters of the system are resampled for every instance, so the result cannot be known in advance, yet it can be scored exactly. Across 30 experiments in five disciplines on 14 apparatus platforms, the agent receives an objective and the apparatus, chooses its own procedure, and operates a physics-based simulated laboratory, reading the instruments through its cameras. Evaluation checks what the agent came to know, grounded in readings recorded during the episode, as well as the physical state the task requires; every experiment is verified to be solvable. We evaluate six frontier models in their developers' coding agents with native observation and control, with added perception and motion planning, and with manipulation skills distilled from the strongest agents. With native control, even the strongest agent succeeds less than half the time; for every agent, most failures arise in interacting with the apparatus, and manipulation skills help weaker agents more than perception and planning. The benchmark and its evaluation code are available at https://github.com/HexaFuture/EmbodiedLab.

cs.RO↗
arXiv2026

Beyond Modeling Order: Dual-Path Spatiotemporal Representation Learning for Cross-Subject EEG Emotion Recognition

Cross-subject generalization remains a major challenge for EEG-based emotion recognition due to pronounced inter-subject variability in neural activity and emotion-related spatiotemporal patterns. Existing methods mainly alleviate inter subject differences through distribution alignment or contrastive learning, while paying limited attention to representation bias associated with fixed spatiotemporal modeling orders. We hypothesize that high-level emotion representations of the same EEG signal should remain consistent across different spatiotemporal modeling paths. Based on this hypothesis, we propose a Dual-Path Spatiotemporal Contrastive Learning (DP-STCL) framework for cross-subject EEG emotion recognition. DP-STCL employs two complementary encoders with independent parameters, namely a Temporal-to-Spatial (TS) path and a Spatial to-Temporal (ST) path, to model EEG spatiotemporal information under different integration orders. During representation learning, the same emotional stimulus is used to establish cross subject associations, while three complementary relations jointly constrain representation variations across subjects and modeling paths. This promotes stable and discriminative stimulus-related emotion representations. To further handle limited labeled target subject data, we introduce a LoRA-based few-shot adaptation strategy with low parameter overhead. Extensive cross-subject experiments on SEED, SEED-IV, SEED-V, and FACED show that DP-STCL consistently outperforms the compared methods, demonstrating its effectiveness in improving cross-subject EEG emotion recognition.

cs.LG↗
arXiv2026

Resolving Primitive-Sharing Ambiguity in Long-Tailed TLS-Based Industrial MEP Point Cloud Segmentation via Spatial Context Constraints

In terrestrial laser scanning (TLS)-based mechanical, electrical, and plumbing (MEP) point cloud segmentation, safety-critical components such as reducers and valves are persistently misclassified, blocking reliable engineering knowledge extraction. This stems from a dual crisis--extreme class imbalance (215:1) compounded by geometric ambiguity, since most tail classes share cylindrical primitives with dominant head classes--that existing frequency-based re-weighting methods cannot resolve. We propose spatial context constraints that exploit neighborhood prediction consistency to disambiguate locally similar structures. Our approach extends Class-Balanced (CB) Loss with two architecture-agnostic mechanisms: Boundary-CB, an entropy-based constraint that emphasizes ambiguous boundaries and encodes an MEP assembly-topology prior, and Density-CB, a density-based constraint that compensates for scan-dependent variations and encodes TLS sensor-physics knowledge. Both operate at the loss level and require no backbone modifications; we evaluate them with ResPointNet++. On the Industrial3D dataset (612.7M labelled points from water treatment facilities), our method achieves 55.74% mIoU on the evaluation split, which also served as the validation split, exceeding the strongest of three backbone baselines (39.83-52.48% mIoU), with a 21.7% relative improvement on tail-class performance (29.59% vs. 24.32%) while preserving head-class accuracy (88.14%). Reducer improves from 0% to 21.12% IoU and valve by 24.3% relative. Evaluated per area, the gain comes from the area rich in these primitive-sharing components (tail mIoU 21.4% to 26.5%), while the other area's mIoU is 0.6 points lower. Spatial context constraints thus reduce primitive-sharing errors in the target MEP setting, supporting more reliable identification of safety-critical components for Digital Twin and Scan-to-BIM applications.

cs.CV↗
arXiv2026

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents

Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly vulnerable to prompt injection attacks, where adversarial instructions embedded in HTML or rendered screenshots can manipulate agent behavior and lead to harmful outcomes such as information leakage. Existing defenses, including system prompt defenses and direct fine-tuning of agents, have shown limited effectiveness. To address this issue, we propose a defense framework in which a web agent operates in parallel with a dedicated guard agent, decoupling prompt injection detection from the agent's own reasoning. Building on this framework, we introduce WebAgentGuard, a reasoning-driven, multimodal guard model for prompt injection detection. We construct a synthetic multimodal dataset using GPT-5 spanning 164 topics and 230 visual and UI design styles, and train the model via reasoning-intensive supervised fine-tuning followed by reinforcement learning. Experiments across multiple benchmarks show that WebAgentGuard consistently outperforms strong baselines while preserving agent utility, without introducing additional latency.

cs.CR↗
arXiv2026

RetryBench: Separating Retry Permission from Recovery Outcomes in GPT Tool Use

False retry permission (FRP) occurs when an agent retries a timed-out tool call without support from the visible contract. RetryBench separates this error from realized recovery. Successful protected recovery does not imply reliable rejection of unsupported retries. In a 720-response key control, valid keys usually enabled safe progress, but offered changed keys elicited unsupported retries in Sol (1/80), Terra (55/80), and Luna (60/80). A later 240-response control removed the candidate and required models to supply a key. Luna still made 8/80 unsupported dispatches; Sol and Terra made none in 80 responses each. Accepting a displayed bad key therefore cannot explain all observed errors, although changed output requirements and conditions preclude a pure display-effect comparison. Removing the weak-contract label increased retries in Sol and Terra's coded-action conditions in a six-endpoint study. A separate 1,536-response canonical-action block also found a positive Terra contrast (115/128 versus 124/128 retries), concentrated in two task/order conditions; the other five contrasts remained unresolved after multiplicity correction. An explicit-contract cue control elicited deferral in all 762 returned responses, leaving recovery unresolved. These results support reporting permission and recovery together across declared interface variants. The evidence covers four purposive tasks, fixed GPT endpoints, and one recovery decision; it identifies neither internal mechanisms nor episode-level safety.

cs.AI↗
arXiv2026

Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization

Recent post-training methods, particularly Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced the reasoning ability of Large Vision-Language Models (LVLMs). However, the sparse nature of verifiable rewards provides little token-level supervision for failed rollouts, often leading to inefficient exploration in complex multimodal reasoning tasks. Although policy distillation can offer dense guidance, external teacher based methods introduce substantial computational overhead, while answer conditioned tuning methods may expose answer-level information and induce shortcut-like generation behavior. To address these limitations, we propose PTD-PO, a Privileged Tutoring Distillation Policy Optimization framework for RLVR that provides dense guidance without exposing the answer to the student policy. Specifically, PTD-PO constructs structured privileged hints from spatial attention guidance and intermediate textual reasoning steps, and uses them through in-context learning to produce step-wise token-distribution supervision. The student is still optimized under the original answer-free context, and its failed rollouts are aligned with the hint-augmented reference model at the token-distribution level. To further stabilize distillation under the distribution shift between guided and unguided contexts, we introduce a Top-K Jensen-Shannon divergence objective that focuses alignment on informative token probabilities while reducing memory overhead. Experiments on LVLMs ranging from 2B to 8B parameters show that PTD-PO consistently outperforms RLVR and distillation baselines, mitigates entropy collapse, and improves complex multimodal reasoning performance.

cs.AI↗
arXiv2026

Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild

AI coding assistants are now widely used in software development. Software developers increasingly integrate AI-generated code into their codebases to improve productivity. Prior studies have shown that AI-generated code may contain code quality issues under controlled settings. However, we still know little about the real-world impact of AI-generated code on software quality and maintenance after it is introduced into production repositories. In other words, it remains unclear whether such issues are quickly fixed or persist and accumulate over time as technical debt. In this paper, we conduct a large-scale empirical study on the technical debt introduced by AI coding assistants in the wild. To achieve that, we built a dataset of 302.6k verified AI-authored commits from 6,299 GitHub repositories, covering five widely used AI coding assistants. For each commit, we run static analysis before and after the change to precisely attribute which code smells, correctness issues, and security issues the AI introduced. We then track each introduced issue from the introducing commit to the latest repository revision to study its lifecycle. Our results show that we identified 484,366 distinct issues, and that code smells are by far the most common type, accounting for 89.3% of all issues. Between 7.5% and 14.8% of each assistant's commits introduce at least one issue. More importantly, 22.7% of tracked AI-introduced issues still survive at the latest version of the repository. These findings show that AI-generated code can introduce long-term maintenance costs into real software projects and highlight the need for stronger quality assurance in AI-assisted development.

cs.SE↗
arXiv2026

OSCAR: Order-aware Sensitivity Correction for AI Rankings

LLM judges evaluate candidate language models through pairwise comparisons of their responses. Judge-aware Bradley--Terry models aggregate pairwise comparisons by jointly estimating candidate scores and judge-specific sensitivities (how strongly each judge responds to quality differences), often interpreted as reliability. We show that this reading fails when judges prefer a display position. Even under balanced display orders or swap-and-average, omitting position attenuates fitted judge sensitivity by approximately the factor $1-D^2$ near equal quality, where $D$ is the judge's net first-slot preference between equally good responses. We propose OSCAR, which jointly estimates candidate scores, judge sensitivities and judge-specific position, length and family effects, and provides confidence intervals for pairwise win probabilities that account for dependence within prompts. On held-out data, observed attenuation closely matches the prediction $1-D^2$ (correlation of log ratios 0.99). Across four datasets, position adjustment lowers held-out log loss by 14-23% and changes which judges would be dropped for low sensitivity on three datasets. On MT-Bench, it ranks GPT-4 first instead of claude-v1, matching human votes. Simulations with known parameters show improved recovery of judge sensitivities and candidate rankings, with 94.4-95.2% confidence interval coverage. Low estimated sensitivity alone is therefore not evidence of an unreliable judge.

stat.ML↗
arXiv2026

Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap

Real-world user behavior rarely consists of isolated actions; instead, it often forms intent flows governed by spatiotemporal dependencies. To provide integrated service recommendations, we focus on the task of Generative Spatiotemporal Intent Sequence Recommendation (GSISR), which aims to generate intent sequences that are logically coherent and physically executable within complex spatiotemporal contexts. While LLMs offer strong reasoning potential for GSISR, direct industrial deployment is limited by high inference latency and context-mismatched or physically infeasible plans. To address these challenges, we propose a generative framework, GPlan, that internalizes LLM reasoning into lightweight models through two components. First, to enable reasoning under strict latency constraints, we introduce Progressive Implicit CoT Distillation, which compresses explicit reasoning processes into reserved latent tokens, allowing small models to inherit complex planning logic without generating long reasoning text. Second, to address the disconnect between general knowledge and real-world constraints, we design Spatiotemporal Counterfactual DPO. By aligning the model with counterfactual context-plan pairs, we improve sensitivity to spatiotemporal context and reduce context-mismatched plans. Offline experiments and online A/B testing demonstrate that our approach improves sequence coherence and context responsiveness. Our implementation and the anonymized GSISR dataset are available at https://github.com/alibaba/GPlan.

cs.IR↗
arXiv2026

Aletheia: Permission-Minimality Testing for Coding-Agent Rules

Coding agents powered by Large Language Models (LLMs) read repository rules (e.g., AGENTS.md and Cursor rules) to learn project conventions and development procedures. An attacker can exploit the same files to mislead the agent into requesting excessive permissions or performing unrelated operations, such as accessing credentials or transferring data. We present Aletheia, a framework for permission-minimality testing of coding-agent rules. It tests whether the permissions requested in these rules are necessary to complete specified tasks. An LLM first translates the rule files into a typed permission language. Aletheia then removes one permission declaration at a time and synthesizes the corresponding restricted sandbox configuration using a trusted task environment. It executes the unchanged rule and task under both the full and restricted configurations. If both executions produce artifacts that pass the functional tests, Aletheia identifies the removed permission as unnecessary for the tested task and flags the corresponding rule file as suspicious. We evaluate Aletheia on AIShellJack, which provides 314 attack rules containing prompt-injection payloads and five benign rules, as well as 80 manually verified benign rules from GHAgentFiles. Aletheia detects all 314 attacks while reporting only three false positives among the 85 benign rules (3.5%). On average, the evaluation takes 44.35 seconds and costs US$0.22 per rule.

cs.CR↗
arXiv2026

Integrated Imputation-Classification for Supervised Learning with Missing Data

We study supervised classification problems with missing feature values. Existing approaches often decouple imputation from classification, producing imputations that may be plausible but uninformative for prediction. Instead, we propose the Integrated Imputation and Classification Network (IICN), which jointly trains an imputer and an ${(n{+}1)}$-classdiscriminator adversarially with a single class supervised classification objective, where the discriminator learns to distinguish among the $n$ true classes and an additional ``imputed" class. We prove that at the global optimum, the imputer and discriminator together implement marginalization over missing coordinates and yield a Bayes-optimal classifier. We evaluate IICN on FashionMNIST, CIFAR-10, and tabular datasets with naturally occurring missingness. IICN outperforms classical impute-then-classify pipelines and recent generative baselines, showing strong robustness and accuracy in challenging settings.

cs.LG↗
arXiv2026

Collective Bias Mitigation via Model Routing and Collaboration

Large language models (LLMs) are increasingly deployed in public health, finance, and governance, requiring both accuracy and societal value alignment. Despite recent advances, LLMs often perpetuate or amplify bias embedded in their training data, posing challenges to fairness. While self-debiasing encourages an LLM to identify and correct its own biases, relying on a single model's intrinsic knowledge may be insufficient to address deeply ingrained stereotypes. To address this limitation, we introduce Collective Bias Mitigation (CBM), a framework that alleviates bias by learning fine-grained model behavior and fostering knowledge sharing among diverse LLMs. This work is the first to systematically explore the effective selection and organization of distinct LLMs to cultivate fairer LLM responses. Experiments show CBM substantially outperforms standalone baselines (e.g., in the top-7 setting, Committee lowers the age bias score from 0.25 to 0.10). Our Debating and Committee topologies achieve substantial bias reduction, with the latter balancing mitigation effectiveness and inference cost, highlighting the potential of CBM for fairer LLMs.

cs.CL↗
arXiv2026

What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use

What should data teach a language model at a particular point in training? A circuit view reveals three distinct bottlenecks: forming a computation, making its required content available, and selecting among available routes. A shared diagnosis-to-data principle connects them: localize the missing operation, preserve its causal relation, vary shortcut-bearing context, and re-audit the residual. Formation-sensitive selection and prerequisite ordering accelerate a binding-matching-transport path; a brief early prefix from the same training multiset retains a validation advantage through 100B tokens. Availability counterfactuals then distinguish writing content from invoking available memory, while paired supervision and context-opportunity ranking improve matched route decisions and long-context answer likelihood. A continuous 350M-model experiment connects the three interventions on the same facts: early circuit training improves subsequent learning, and the complete sequence outperforms stage-replacement controls on facts withheld from Use teaching. Independent query surfaces and opposed-source decisions expose conditional arbitration as the remaining frontier. Together, these results show why a change in the limiting operation calls for a change in supervision, not merely a new ranking of difficult examples.

cs.LG↗
arXiv2026

PRISM: Parallel Residual Iterative Sequence Model

Generative sequence modeling faces a fundamental tension between the expressivity of Transformers and the efficiency of linear sequence models. Existing efficient architectures are theoretically bounded by shallow, single-step linear updates, while powerful iterative methods like Test-Time Training (TTT) break hardware parallelism due to two dimensions of serial dependency: token-level state reliance and step-level iteration loops. We propose PRISM (Parallel Residual Iterative Sequence Model) to resolve this tension. PRISM explicitly approximates the expressive gate-residual-direction iteration pattern of TTT in a parallelizable form. We employ a Write-Forget Decoupling strategy that isolates non-linearity within the injection operator. To bypass the serial dependency of explicit solvers, PRISM utilizes a two-stage proxy architecture: a short-convolution anchors the initial residual using local history energy, while a learned predictor estimates the refinement updates directly from the input. This design distills structural patterns associated with iterative correction into a parallelizable feedforward operator. Theoretically, we prove that this formulation achieves Rank-$L$ accumulation, structurally expanding the update scheme beyond the single-step Rank-$1$ bottleneck. Empirically, it achieves comparable performance to explicit optimization methods while achieving \textbf{174x higher throughput}. Codes are available in https://github.com/gpr-prism/prism/.

cs.LG↗
arXiv2026

The Token Before the Value Is the Key: How Hybrid Architectures Organize Induction Circuits

Hybrid language models can improve capability as well as efficiency, raising the question of how architectural complementarity becomes learned computation. We examine the established induction roles of Carrying predecessor information, Matching a source by content, and Copying its value. How are these position-sensitive and content-based computations allocated across heterogeneous layers? We introduce layer-type-agnostic paired probes that track Carrying and Matching through a common block-update interface. In recurrent--global and local--global hybrids, Carrying concentrates in efficient layers and Matching in global receivers. The measured local contribution concentrates on lag one: the token immediately before the historical value. Changing predecessor support through lag-one masking, convolution removal, or early learning-rate reduction can relocate Carrying and Matching between stages. Source-key restoration and fixed-value selection trace the receiver's dependence on the prepared source. These interventions also change natural-text recall, with outcomes depending on configuration and target. Varying local windows and induction-enriched training text changes the early development of functional Carrying and Matching, connecting architectural priors and training evidence to formation timing. Together, the probes and interventions shift the explanatory focus upstream: the organization of Matching follows how Carrying is learned. The token before the value provides a concrete link between a hybrid's architecture, circuit development, and recall. Code is available in https://github.com/ckpassenger/bind-match-copy/tree/main.

cs.LG↗
arXiv2026

Cognitive Link-Flexible FTN-OTFS Design for High-Mobility LEO Satellite Communications

Low Earth orbit (LEO) satellite links are challenged by pronounced signal-to-noise ratio (SNR) variation and severe Doppler shifts. Although mobility robustness is provided by orthogonal time frequency space (OTFS) modulation, the rate-reliability tradeoff of faster-than-Nyquist (FTN) signaling is constrained by fixed packing. In this paper, an SNR-aware flexible FTN-OTFS framework is proposed, in which the packing factor is adapted to changing link conditions under a prescribed reliability requirement. Link-state perception and packing decisions are supported by estimated SNR and offline reliability thresholds, with constant decision complexity achieved through a fixed-mode lookup table. Elevation-dependent propagation, fractional Doppler, and FTN-induced interference are incorporated into the signal model, while colored noise is accommodated by covariance-aware linear minimum mean-square error detection. Throughput and bit error rate are analytically characterized, and energy efficiency and peak-to-average power ratio are evaluated. Simulation results show that conservative packing preserves reliability under unfavorable conditions, while denser signaling improves throughput as the link strengthens. These findings highlight the potential of cognitive FTN adaptation for efficient future LEO wireless communications.

cs.IT↗